Qwen Code v0.16.2

<!-- Release notes generated using configuration in .github/release.yml at release/v0.16.2 --> ## What's Changed * fix(build): clean stale outputs before tsc --build to prevent TS5055 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4453 * chore(release): v0.16.1 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/4467 * feat(cli): do not append trailing space for directory completions (#4092) by @dykebo in https://github.com/QwenLM/qwen-code/pull/4288 * feat(skills): add memory-leak-debug skill for heap snapshot diagnosis by @huww98 in https://github.com/QwenLM/qwen-code/pull/4468 * fix(cli): resolve stale closure race in text buffer submit handler by @huww98 in https://github.com/QwenLM/qwen-code/pull/4470 * fix(weixin): allow Windows image paths inside workspace by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4465 * fix(weixin): send decryptable image payloads by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4464 * feat(memory): load .qwen/QWEN.local.md as project-local context (#4091) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4394 * fix(core): preserve duplicate object references in safeJsonStringify by @ihubanov in https://github.com/QwenLM/qwen-code/pull/4407 * fix(extension): redact credentialed source diagnostics by @qqqys in https://github.com/QwenLM/qwen-code/pull/4426 * feat(core): limit background agent concurrency by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/4324 * fix(core): strip additional dangerous interpreter rules by @qqqys in https://github.com/QwenLM/qwen-code/pull/4371 * docs(tools): document monitor tool by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4356 * docs(agents,pr-template): add Working Principles and restructure PR template by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4496 * ci: split Aliyun OSS sync into a separate post-release workflow by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4492 * feat(core): enable Token Plan cache control by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4495 * feat(core)!: redesign auto-compaction thresholds with three-tier ladder by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4345 * feat(telemetry): client-side HTTP span + opt-in W3C traceparent propagation (#4384) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4390 * feat(cli): headless / non-interactive runaway-protection guardrails (#4103) by @BZ-D in https://github.com/QwenLM/qwen-code/pull/4502 * fix(cli): require whitespace before @ to trigger file completion by @wenshao in https://github.com/QwenLM/qwen-code/pull/4487 * fix(auth): align Token Plan model defaults with ModelStudio by @YingchaoX in https://github.com/QwenLM/qwen-code/pull/4478 * fix(extension): populate resources when Claude marketplace points at whole folder by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4497 * fix(cli): align /context token breakdown with actual API request by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4512 * fix(sdk): honor canUseTool timeout in CLI control requests by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4491 * fix(core): stop AbortSignal listener leak in long sessions (MaxListenersExceededWarning) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4366 * feat(cli): dense inline panel + keyboard navigation for parallel agent fan-out by @wenshao in https://github.com/QwenLM/qwen-code/pull/4477 * fix(core): prevent auto-skill creation from overwriting existing skills (#4437) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4489 * fix(sdk): Include CLI chunks in SDK package by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4541 * fix(cli): persist MCP server removals by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4535 * fix(models): refresh raw model-derived defaults by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4517 * fix(vscode-ide-companion): exclude workspace packages from NOTICES.txt generation by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4455 * fix(telemetry): attach interaction span to session root context by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4499 * fix(cli): auto-prepend @ when pasting or dropping multiple file paths by @MikeWang0316tw in https://github.com/QwenLM/qwen-code/pull/4544 * feat(prompt): move new app prompt from system prompt to skills by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4567 * feat(worktree): Phase D — startup --worktree flag + symlinkDirectories + PR refs by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4381 * fix(permissions): make command substitution ask, not deny (#4093) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4386 * feat(cli): default auto-dream/auto-skill to on and add /memory toggle by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4547 ## New Contributors * @dykebo made their first contribution in https://github.com/QwenLM/qwen-code/pull/4288 **Full Changelog**: https://github.com/QwenLM/qwen-code/compare/v0.16.1...v0.16.2